[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-366877-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-366877-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","riva-an-image-dataset-of-conventional-pap-smear-cytology-with-multiple-independent-annotations","RIVa - an Image Dataset of Conventional Pap Smear Cytology with Multiple Independent Annotations","","RIVa introduces a high-resolution image dataset for conventional Pap smear cytology, built to support robust AI training and evaluation. The collection includes 959 scanned images (1024 × 1024 px) from 115 patients, annotated by up to four independent medical professionals using Bethesda classification. Multiple expert labels provide nucleus coordinates and classification targets. Inter-annotator consistency is reported with strong agreement for lesion vs non-lesion and across the full Bethesda eight-category scheme, enabling both consensus ground truth and reliability analysis.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/riva-an-image-dataset-of-conventional-pap-smear-cytology-with-multiple-independent-annotations/366877/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/riva-an-image-dataset-of-conventional-pap-smear-cytology-with-multiple-independent-annotations/366877.png","ImageObject",300,407,{"name":42,"@type":43},"mieayamfan","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-10","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is RIVa and what problem does it address?","Question",{"text":63,"@type":64},"RIVa is a high-resolution image dataset for conventional Pap smear cytology. It addresses the lack of large, high-quality, and diverse publicly available cytology image datasets for training generalizable AI models.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How are the images labeled in RIVa?",{"text":68,"@type":64},"Each image is annotated by up to four independent medical professionals. Labels follow the Bethesda classification and include nucleus coordinates plus classification targets.",{"name":70,"@type":61,"acceptedAnswer":71},"What does the dataset enable beyond training models?",{"text":72,"@type":64},"Multiple expert annotations provide consensus-driven ground truth for robust AI training and also allow inter-annotator consistency analysis using reported agreement rates.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},366877,1790325197,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":107,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":33,"preview_urls":146},962090893677,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \nOpEN  \nDATA DESCRIpTOR  \nRIVa: an Image Dataset of Conventional Pap Smear Cytology with Multiple Independent annotations  \nPaula Perez Bianchi1, Sol anselmo2,10, MalenaVásquez Currié2,10, Jimena Medel3, Estefanía Uelf3, alicia Dos Santos3, Noemí Buosi3, Rosana Vargas3,4, Juliana Reves Szemere5, Bruno Volcovinsky2, Hugo Massaroli1, Manuel andrade6, alejandro Monastra7,8, Emmanuel Iarussi6,8, Viviana Siless4,6 & Luciana Bruno8,9 ✉  \nthe Pap smear remains the primary screening test for cervical cancer in many low-resource regions, yet publicly available image datasets largely feature liquid-based preparations. We introduce RIVa, a high-resolution collection of 959 conventional-smear images (1024 × 1024 px) scanned at 40x magnification, sourced from 115 patients. To ensure label quality, each image was annotated by up to four independent medical professionals, with 42% of the images reviewed by all four, resulting in 26,158 annotations based on the Bethesda classification. Annotations provide coordinates of nuclei and classification labels by up to four annotators. The dataset includes 15,949 unique cells across five (pre) cancerous types (SCC, HSIL, ASCH, LSIL, ASCUS) and three non-lesion categories (NILM, ENDO, INFL) . These four-expert annotations not only give RIVA a consensus-driven ground truth for robust AI training but also enable inter-annotator consistency analysis-agreement rates reach 94% for lesion vs. nonlesion and 74% across the full eight-category Bethesda scheme.  \nBackground & Summary  \nCervical cancer is one of the most preventable forms of cancer, yet it remains a significant public health challenge worldwide, particularly in low-and middle-income countries (LMICs) where access to screening programs is limited. Globally, over 600,000 new cases and more than 340,000 deaths were reported in 2020 alone, with nearly 90% of these deaths occurring in LMICs1. Early detection and classification of cervical lesions are crucial, as they significantly increase the chances of successful treatment and long-term survival.  \nPapanicolaou (Pap) smear screening has proven highly effective in reducing the incidence and mortality associated with cervical cancer2. However, conventional cytology requires manual inspection of stained cell samples-a time-consuming and expertise-dependent process that is susceptible to human error, inter-observer variability, and reduced sensitivity and reproducibility, especially under high workloads3. These limitations posea serious barrier to widespread and equitable implementation, particularly in settings with constrained healthcare resources.  \nRecent advances in artificial intelligence (AI), particularly deep learning, have enabled the automation of numerous medical imaging tasks, achieving or even surpassing expert-level performance in certain domains4. Despite these advancements, the application of AI to cytology remains relatively underdeveloped, and its clinical  \n1 Departamento de computación (Dc), facultad de ciencias exactas y naturales, Universidad de Buenos Aires (UBA), Buenos Aires, Argentina. 2instituto tecnológico de Buenos Aires (itBA), Buenos Aires, Argentina. 3Servicio deAnatomía Patológica, Hospital Bernardino Rivadavia, Buenos Aires, Argentina. 4Pathology & Molecular Biology Laboratories, Biomakers, Buenos Aires, Argentina. 5escuela de ciencia y tecnología, Universidad nacional de San Martín, Buenos Aires, Argentina. 6 Universidad torcuato Di tella (UtDt), Buenos Aires, Argentina. 7 instituto de ciencias, Universidad nacional de General Sarmiento, Buenos Aires, Argentina. 8consejo nacional de investigaciones Científicas y Técnicas (CONICET), Buenos Aires, Argentina. 9instituto de cálculo (ic), facultad de ciencias exactas ynaturales, Universidad de Buenos Aires (UBA), Buenos Aires, Argentina. 10these authors contributed equally: Sol Anselmo, MalenaVásquez Currié . ✉ e-mail: [luciana.bruno@ic.fcen.uba.ar](luciana","cbCaidrHZ3cox3AY","https://ap.wps.com/l/cbCaidrHZ3cox3AY","pdf",2580843,"English","# Background & Summary\n## Public health need and screening limits\n## Conventional cytology workflow and challenges\n## AI advances and remaining gaps\n# Dataset design and annotation protocol\n## Image sourcing and acquisition\n## Bethesda-based labeling by multiple experts\n## Cell and class composition\n## Consistency analysis and agreement rates\n# Comparison with existing datasets","[{\"question\":\"What is RIVa and what problem does it address?\",\"answer\":\"RIVa is a high-resolution image dataset for conventional Pap smear cytology. It addresses the lack of large, high-quality, and diverse publicly available cytology image datasets for training generalizable AI models.\"},{\"question\":\"How are the images labeled in RIVa?\",\"answer\":\"Each image is annotated by up to four independent medical professionals. Labels follow the Bethesda classification and include nucleus coordinates plus classification targets.\"},{\"question\":\"What does the dataset enable beyond training models?\",\"answer\":\"Multiple expert annotations provide consensus-driven ground truth for robust AI training and also allow inter-annotator consistency analysis using reported agreement rates.\"}]","RIVa - an Image Dataset of Conventional Pap Smear Cytology with Multiple Independent Annotations | PDF",1790168086,18,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/aea738fff183d58dd45b994d628de9f6.webp",983,1291,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/b540c43c43bcb5f7f39a68ffb55643a6.webp",982,1290,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ba7de8f7dec60fcd7671532fab7cf5af.webp",981,1289,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ac58cc82171cc33bf3c5e586ac527c22.webp",980,1287]